gms | German Medical Science

Learning through Inquiry in Higher Education: Current Research and Future Challenges (INHERE 2018)

08.03. - 09.03.2018, München

Active open online learning: A practical approach to improving statistical literacy among learners

Meeting Abstract

Suche in Medline nach

Learning through Inquiry in Higher Education: Current Research and Future Challenges (INHERE 2018). München, 08.-09.03.2018. Düsseldorf: German Medical Science GMS Publishing House; 2018. Doc42

doi: 10.3205/18inhere42, urn:nbn:de:0183-18inhere429

Veröffentlicht: 1. März 2018

© 2018 Herrera-Bennett.
Dieser Artikel ist ein Open-Access-Artikel und steht unter den Lizenzbedingungen der Creative Commons Attribution 4.0 License (Namensnennung). Lizenz-Angaben siehe



Background: With the rise of technology in educational design, massive open online courses (MOOCs) are becoming more popular to facilitate teaching and learning, emphasizing open-access, interactive, and self-paced instruction. Such platforms have been invoked to improve statistical education among students and researchers. While the current work assesses individual learners, it speaks to a larger concern within psychology, namely the replicability crisis (OSC, 2015), raising doubts about methodological & statistical rigour among psychologists and social scientists. In light of overwhelming prevalence rates of p-value misinterpretations [1], [2], [3], research is warranted in pinpointing statistical misconceptions, and developing means to improve statistical literacy – goals that should be tackled in unison.

Methods: Pre-/posttest design is implemented within Daniёl Lakens’ 8-week MOOC “Improving your statistical inferences”, which fosters practical understanding of statistical concepts through use of mixed instructional methods, including video lectures and hands-on assignments (e.g., R simulations). The current research evaluates the effectiveness of this applied approach when teaching correct interpretations of p-values, confidence intervals (CIs), and Bayes Factors (BFs). 3 measurement timepoints (14 True/False questions), serve as proxies of prior knowledge (in week 1), immediate improvement (across weeks 1-4), and retention (in week 8). Repeated-measures ANCOVA and regression analyses are used to evaluate effects of course participation on learning, with additional separate analyses for each concept (p-values, CIs, BFs). Demographics and confidence ratings are measured.

Results & Discussion: Study is currently in the online data collection phase. Based on our pilot findings, we expect accuracy rates to correlate with confidence levels and self-rated statistical expertise. Results will be discussed in relation to conceptual knowledge gain vs. applied learning, and how each form of inferential reasoning might inform the other. The presented research aims to instill a more positive outlook on the matter of improving statistical literacy, using practical hands-on learning platforms that may cultivate inquiry-based learning processes.


Oakes MW. Statistical inference. Chestnut Hill, MA: Epidemiology Resources; 1986.
Haller H, Krauss S. Misinterpretations of significance: A problem students share with their teachers. Method Psychol Res. 2002;7(1):1-20.
Badenes-Ribera L. Frías-Navarro D, Monterde-i-Bort H, Pascual-Soler M. Interpretation of the p value: A national survey study in academic psychologists from Spain. Psicothema. 2015;27(3):290-295.